Quick setup on linux: STEP 0: install/download llama.cpp, Freecad, your favourite gguf model - possibly with multimedia image reading capabilities (I've used Qwen3.8-27B-UD-Q4_K_M and relative mmproj-F16 quantized by Unsloth), uv (, pi.dev) STEP 1: $ cd /your/path/to/ (i.e. where to install) STEP 2: